debrief-coding

debrief-coding is a skill for Claude Code, Codex from Borda/AI-Rig. It costs 69 tokens per session (2,564 once invoked), scanned A, original, Apache-2.0.

A diagnostic report tool for codemap usage logs. It reads recorded command and tool activity, optionally filters it by date or session, and can anonymize names before sharing.

In plain words
What is it for?
Use it to analyse recent codemap activity, debug errors, or create an anonymized report of CLI, skill, and tool logs.
Why use it?
It helps investigate failed queries, usage patterns, and gaps in telemetry without exposing project identifiers in the report.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the codemap-py plugin — 6 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/borda/ai-rig/debrief-coding
Any agent
npx skills add Borda/AI-Rig --skill debrief-coding
Clone the repo
git clone --depth 1 https://github.com/Borda/AI-Rig

Made for: Claude Code, Codex.

Or install codemap-py, the plugin that ships this one along with the rest of its 6 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for debrief-coding

README.md
[![agentmods](https://agentmods.dev/badge/skills/borda/ai-rig/debrief-coding.svg)](https://agentmods.dev/skills/borda/ai-rig/debrief-coding)
Your own site
<a href="https://agentmods.dev/skills/borda/ai-rig/debrief-coding"><img src="https://agentmods.dev/badge/skills/borda/ai-rig/debrief-coding.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,564 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00069 $0.02564
Opus 5 $0.00034 $0.01282
Sonnet 5 $0.00014 $0.00513
Haiku 4.5 $0.00007 $0.00256

Measured yesterday against content hash ad1bdb68545f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debrief-coding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/codemap-py/claude-skills/debrief-coding/SKILL.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read .cache/codemap/logs/ JSONL telemetry; analyze usage; write diagnostic report. Discover legacy flat shards + recursive claude/, codex/, direct/ trees; keep legacy records unattributed. Codex hooks supply runtime-scoped CLI/tool shards, no skill-start events; missing skill telemetry and cross-layer joins remain evidence gaps.

NOT for: validating codemap installation health/integration (use /codemap-py:integration audit); building/querying structural index (use /codemap-py:scan-codebase or /codemap-py:query-code).

Flags

  • --since <YYYY-MM-DD> — filter to records on or after this date (default: all)
  • --session <id> — filter to a single session UUID
  • --anonymize — run anonymize.py on every log shard of all three layers (CLI, skill, tool) before reading; replaces qualified names with stable pseudonyms; keeps salt in .cache/codemap/logs/.salt (never included in output). Directory input preserves runtime topology below the export root and pseudonymizes shard session stems.
  • --output <path> — write report to this path (default: .reports/codemap/debrief-<YYYY-MM-DD>.md)

Step 0: Verify logs exist

find .cache/codemap/logs -type f -name '*.jsonl' -print 2>/dev/null  # timeout: 5000

No files → stop: "No codemap telemetry found. Run any /codemap-py:* skill or codemap-py query/index command to start collecting logs."

Per-session shards under logs/claude/, logs/codex/, logs/direct/: CLI cli_<session>.jsonl; skill skills_<session>.jsonl; tool tools_<session>.jsonl. Older flat shards = unattributed legacy evidence. Collect every matching shard recursively, not only root glob. Preserve topology; report overall, per-runtime, unattributed summaries. token_measurement unavailable: host hooks provide no token usage.

Step 1: Optionally anonymize

If --anonymize flag given:

Guard: anonymize every present CLI, skill, tool shard by passing log directory as --input; recursion covers flat + runtime shards. Copies land in .cache/codemap/export/ with same topology. anonymize.py refuses writes beside .salt; never target logs dir. Step 2 must not mix anonymized/original data or exempt a layer.

Read the full file on GitHub · 190 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 190 lines · 0 tokens per session scan A ad1bdb68545f

Subscribe to this mod's changes

debrief-coding is a skill published in the GitHub repository Borda/AI-Rig (26 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 2,564 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

file-headers

MANDATORY for every coding agent (Claude Code, Codex, or any other) on every change-set — every applicable source file the agent creates or updates MUST start with the project's copyright/authorship header (file overview + exact author line). Use automatically whenever writing a new file or editing an existing one; do…

hoangsonww/Claude-Code-Agent-Monitor · 101 tokens

productivity-score

Calculate a productivity score using actual Agent Monitor metrics — session completion rates, cache efficiency (cacheread vs input), compaction pressure (baseline tokens), turn velocity (turncount / totalturndurationms), tool success ratio (PreToolUse vs PostToolUse), and the workflow intelligence API's complexity and…

hoangsonww/Claude-Code-Agent-Monitor · 67 tokens

budget-set

Define a spend budget for Claude Code and, optionally, create a cost alert rule that fires when usage crosses the limit, via POST /api/alerts/rules on the Agent Monitor dashboard. Reads current spend from /api/pricing/cost to size the budget sensibly and explains every rule field before writing. Use when setting a…

hoangsonww/Claude-Code-Agent-Monitor · 79 tokens

dashboard-status

Quick dashboard health and status overview — checks the Agent Monitor API (port 4820), reports session/agent/event counts from /api/stats, confirms WebSocket connectivity, reads the redacted hook status returned by /api/settings/info, and shows data freshness (last event timestamp). Use to verify the monitoring system…

hoangsonww/Claude-Code-Agent-Monitor · 69 tokens

dag-map

Render the multi-agent orchestration DAG for a session — parent→child subagent edges, tree depth, and fan-out — from the Agent Monitor workflow intelligence API. Cross-checks the orchestration dataset against the raw agent records and session detail. Use when visualizing how a session's agent structure was organized.

hoangsonww/Claude-Code-Agent-Monitor · 65 tokens

run-agent

Launch and supervise Claude Code or Codex through the CCAM Run API. Use when the user wants to start a monitored agent, select a model, approval policy, sandbox, or working directory, send a follow-up, inspect live output, resume a native session, or stop a dashboard-launched run.

hoangsonww/Claude-Code-Agent-Monitor · 64 tokens